© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2914
    Prev
    Next
    INDEX
    Explanations

    references to official notes or memos

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.87
     OFDb
    -0.86
     resourceCulture
    -0.73
     disambiguazione
    -0.68
     décid
    -0.61
    хьтан
    -0.61
     Вікі
    -0.60
     chrétienne
    -0.60
     passés
    -0.60
     AssemblyVersion
    -0.59
    POSITIVE LOGITS
     memo
    0.66
     letter
    0.65
    Preface
    0.54
    icot
    0.52
    MEMORANDUM
    0.52
    pekt
    0.51
    月号
    0.51
    edict
    0.51
     "|"
    0.51
    iqué
    0.51
    Activations Density 0.729%

    No Known Activations